Animating characters using nonparametric regression

Yun Feng Chou*, Zen-Chung Shih

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we propose an image deformation technique using nonparametric regression to animate characters in a still image for multimedia applications. The proposed approach effectively produces a sequence of contiguous frames in an animation. It automatically generates deformed shapes by using elliptic radial basis functions (ERBFs) and locally weighted regression (LOESS). ERBFs are used for representing the deformed character's shapes in synthesized frames. For preserving the pattern within a shape, LOESS is applied to fit the detail with local control. Furthermore, the results show the synthesized frames without unnatural distortion.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Computer Science and Its Applications, CSA 2008
Pages191-198
Number of pages8
DOIs
StatePublished - 28 Nov 2008
Event2008 International Symposium on Computer Science and its Applications, CSA 2008 - Hobart, TAS, Australia
Duration: 13 Oct 200815 Oct 2008

Publication series

NameProceedings - International Symposium on Computer Science and Its Applications, CSA 2008

Conference

Conference2008 International Symposium on Computer Science and its Applications, CSA 2008
CountryAustralia
CityHobart, TAS
Period13/10/0815/10/08

Fingerprint Dive into the research topics of 'Animating characters using nonparametric regression'. Together they form a unique fingerprint.

Cite this